Cost-Effective Foliage Penetration Human Detection Under Severe Weather Conditions Based on Auto-Encoder/Decoder Neural Network

2019 ◽  
Vol 6 (4) ◽  
pp. 6190-6200 ◽  
Author(s):  
Yan Huang ◽  
Yi Zhong ◽  
Qiang Wu ◽  
Eryk Dutkiewicz ◽  
Ting Jiang
Keyword(s):  
Neural Network ◽  
Cost Effective ◽  
Weather Conditions ◽  
Severe Weather ◽  
Human Detection

Development of subsea tie-backs in challenging environments

2014 ◽  
Vol 54 (2) ◽  
pp. 540
Author(s):  
Gregor Couper ◽  
Sina Roshan-Zamir ◽  
John Rickman ◽  
Chris Lee
Keyword(s):  
Cost Effective ◽  
Weather Conditions ◽  
Severe Weather ◽  
Short Length ◽  
Effective Solution ◽  
Established Method ◽  
Constraint Factors ◽  
Successful Execution ◽  
Stage Process

Tie-backs to existing facilities are a long established method of expanding developments, as they often offer a cost-effective solution. For short length tie-backs located in regions that are remote and/or subject to severe weather conditions, however, the feasibility of installation can become a significant constraint. Factors such as high mobilisation cost of pipelay vessels and conditions that make pipeline towing impractical limit the potential design solutions. Defining these constraints early in the project is critical to successful execution. This extended abstract explores the challenges faced when developing such a tie-back by considering a case study of Origin Energy’s Geographe development, located in the Otway Basin. The location and harsh weather conditions constrained the viable installation options, which shaped the design. A flexible flowline was selected because it could be installed from a wider range of vessels and in a less limiting weather window. Subsea coolers are located at the wells for control of top of line (TOL) corrosion and to protect the flexible flowline from exposure to overly high temperatures. The cooler design brings its own challenges, requiring a two-stage process. First, modelling of the production fluid is used to determine the cooling requirements; then, CFD is used to design the cooler piping and structure to achieve this. A design with multiple, smaller structures was used to maximise the number of capable installation vessels. This extended abstract discusses the constraints that can occur, how the design must accommodate them, and the implications on execution of the project.

scholarly journals Outdoor Illegal Parking Detection System Using Convolutional Neural Network on Raspberry Pi

2018 ◽  
Vol 7 (3.7) ◽  
pp. 17
Author(s):  
Chin Kit Ng ◽  
Soon Nyean Cheong ◽  
Wen Wen-Jiun Yap ◽  
Yee Loo Foo
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Detection System ◽  
Cost Effective ◽  
Weather Conditions ◽  
Recall Rate ◽  
Raspberry Pi ◽  
Ip Camera ◽  
Parking Lot ◽  
Precision Rate

This paper proposes a cost-effective vision-based outdoor illegal parking detection system, iConvPark, to automatize the detection of illegally parked vehicles by providing real-time notification regarding the occurrences and locations of illegal parking cases, thereby improving effectiveness of parking rules and regulations enforcement. The iConvPark is implemented on a Raspberry Pi with the use of Convolutional Neural Network as the classifier to identify illegally parked vehicles based on live parking lot image retrieved via an IP camera. The system has been implemented at a university parking lot to detect illegal parking events. Evaluation results show that our proposed system is capable of detecting illegally parked vehicles with precision rate of 1.00 and recall rate of 0.94, implying that the detection is robust against changes in light intensity and the presence of shadow effects under different weather conditions, attributed to the superiority offered by CNN.  

Erbium/Ytterbium-Doped Waveguide Amplifier (EYDWA) for extended reach of Wavelength Division Multiplexing based free space optics system (WDM/FSO)

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Bentahar Attaouia ◽  
Kandouci Malika ◽  
Ghouali Samir
Keyword(s):  
Wavelength Division Multiplexing ◽  
Free Space ◽  
Cost Effective ◽  
Weather Conditions ◽  
Free Space Optical ◽  
Wavelength Division ◽  
Space Optics ◽  
Effective Implementation ◽  
Transmission Distance ◽  
The Cost

AbstractThis work is focused to carry out the investigation of wavelength division multiplexing (WDM) approach on free space optical (FSO) transmission systems using Erbium Ytterbium Doped Waveguide Amplifier (EYDWA) integrated as post-or pre-amplifier for extending the reach to 30 Km for the cost-effective implementation of FSO system considering weather conditions. Furthermore, the performance of proposed FSO-wavelength division multiplexing (WDM) system is also evaluated on the effect of varying the FSO range and results are reported in terms of Q factor, BER, and eye diagrams. It has been found that, under clear rain the post-amplification was performed and was able to reach transmission distance over 27 Km, whereas, the FSO distance has been limited at 19.5 Km by using pre-amplification.

scholarly journals Performance Evaluation of Neural Network-Based Short-Term Solar Irradiation Forecasts

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3030
Author(s):  
Simon Liebermann ◽  
Jung-Sup Um ◽  
YoungSeok Hwang ◽  
Stephan Schlüter
Keyword(s):  
Neural Network ◽  
Goodness Of Fit ◽  
Renewable Energy Sources ◽  
Weather Conditions ◽  
Solar Irradiation ◽  
Weather Data ◽  
Short Term ◽  
Climate Conditions ◽  
Lstm Network ◽  
The Time Domain

Due to the globally increasing share of renewable energy sources like wind and solar power, precise forecasts for weather data are becoming more and more important. To compute such forecasts numerous authors apply neural networks (NN), whereby models became ever more complex recently. Using solar irradiation as an example, we verify if this additional complexity is required in terms of forecasting precision. Different NN models, namely the long-short term (LSTM) neural network, a convolutional neural network (CNN), and combinations of both are benchmarked against each other. The naive forecast is included as a baseline. Various locations across Europe are tested to analyze the models’ performance under different climate conditions. Forecasts up to 24 h in advance are generated and compared using different goodness of fit (GoF) measures. Besides, errors are analyzed in the time domain. As expected, the error of all models increases with rising forecasting horizon. Over all test stations it shows that combining an LSTM network with a CNN yields the best performance. However, regarding the chosen GoF measures, differences to the alternative approaches are fairly small. The hybrid model’s advantage lies not in the improved GoF but in its versatility: contrary to an LSTM or a CNN, it produces good results under all tested weather conditions.

Deep convolutional neural networks for human movement detection using wireless signals

2021 ◽  
pp. 1-10
Author(s):  
Chien-Cheng Leea ◽  
Zhongjian Gao ◽  
Xiu-Chi Huanga
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Convolutional Neural Network ◽  
Detection System ◽  
Deep Convolutional Neural Network ◽  
Human Detection ◽  
Two Dimensional ◽  
Dimensional Matrix ◽  
State Classification ◽  
Propagation Paths

This paper proposes a Wi-Fi-based indoor human detection system using a deep convolutional neural network. The system detects different human states in various situations, including different environments and propagation paths. The main improvements proposed by the system is that there is no cameras overhead and no sensors are mounted. This system captures useful amplitude information from the channel state information and converts this information into an image-like two-dimensional matrix. Next, the two-dimensional matrix is used as an input to a deep convolutional neural network (CNN) to distinguish human states. In this work, a deep residual network (ResNet) architecture is used to perform human state classification with hierarchical topological feature extraction. Several combinations of datasets for different environments and propagation paths are used in this study. ResNet’s powerful inference simplifies feature extraction and improves the accuracy of human state classification. The experimental results show that the fine-tuned ResNet-18 model has good performance in indoor human detection, including people not present, people still, and people moving. Compared with traditional machine learning using handcrafted features, this method is simple and effective.

scholarly journals Detection of Strawberry Diseases Using a Convolutional Neural Network

Plants ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 31
Author(s):  
Jia-Rong Xiao ◽  
Pei-Che Chung ◽  
Hung-Yi Wu ◽  
Quoc-Hung Phan ◽  
Jer-Liang Andrew Yeh ◽  
...  
Keyword(s):  
Neural Network ◽  
Powdery Mildew ◽  
Convolutional Neural Network ◽  
Image Recognition ◽  
Cost Effective ◽  
Gray Mold ◽  
Leaf Blight ◽  
Crown Rot ◽  
Accuracy Rate ◽  
Fruit Disease

The strawberry (Fragaria × ananassa Duch.) is a high-value crop with an annual cultivated area of ~500 ha in Taiwan. Over 90% of strawberry cultivation is in Miaoli County. Unfortunately, various diseases significantly decrease strawberry production. The leaf and fruit disease became an epidemic in 1986. From 2010 to 2016, anthracnose crown rot caused the loss of 30–40% of seedlings and ~20% of plants after transplanting. The automation of agriculture and image recognition techniques are indispensable for detecting strawberry diseases. We developed an image recognition technique for the detection of strawberry diseases using a convolutional neural network (CNN) model. CNN is a powerful deep learning approach that has been used to enhance image recognition. In the proposed technique, two different datasets containing the original and feature images are used for detecting the following strawberry diseases—leaf blight, gray mold, and powdery mildew. Specifically, leaf blight may affect the crown, leaf, and fruit and show different symptoms. By using the ResNet50 model with a training period of 20 epochs for 1306 feature images, the proposed CNN model achieves a classification accuracy rate of 100% for leaf blight cases affecting the crown, leaf, and fruit; 98% for gray mold cases, and 98% for powdery mildew cases. In 20 epochs, the accuracy rate of 99.60% obtained from the feature image dataset was higher than that of 1.53% obtained from the original one. This proposed model provides a simple, reliable, and cost-effective technique for detecting strawberry diseases.

scholarly journals Terminal Airspace Capacity Evaluation Model under Weather Condition from Perspective of a Controller

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Lu Liu
Keyword(s):  
Network Flow ◽  
Topological Structure ◽  
Evaluation Model ◽  
Weather Condition ◽  
Weather Conditions ◽  
Severe Weather ◽  
Safe Operation ◽  
Weather Factor ◽  
Route Network ◽  
Capacity Evaluation

A route network lays in the terminal airspace. The route network can be divided into multiple subnetworks according to sectors. When severe weather conditions occur, a controller takes measures to obtain safe operation of flights, such as navigation guidance or changing the availability of routes. In such circumstances, the route structure of a subnetwork is changed, and the controller’s attention paid to each route is also changed as well as the unit workload on it. As the subnetwork is handled by one controller, capacities of routes in it are associated. We find the way to determine the “related capacity” of a route in the conditions that whether topological structure of the terminal route network is changed or not. The capacity of the terminal route network calculated by network flow theory represents the capacity of terminal airspace. According to the analysis results, the weather factor reduces capacity of terminal airspace directly by reducing the capacities of routes blocked. Indirectly, it diverts controller’s attention to change capacities of other routes in the subnetwork.

Sign in / Sign up

Export Citation Format

Share Document